[codex] Fail OpenCode approve when review publish fails#272
Open
seonghobae wants to merge 11 commits into
Open
[codex] Fail OpenCode approve when review publish fails#272seonghobae wants to merge 11 commits into
seonghobae wants to merge 11 commits into
Conversation
There was a problem hiding this comment.
Pull request overview
This PR updates the OpenCode review workflow to fail the APPROVE gate when publishing the approving GitHub pull review fails, removing the prior “rate-limit soft-pass” behavior that could leave branch protection requirements unsatisfied.
Changes:
- Remove the rate-limit detection/soft-pass path for APPROVE pull-review publication failures.
- Fail the workflow when pull-review publication fails (so the PR cannot appear “approved” without an actual GitHub approval review).
- Tighten the shell regression gate to assert the “skipped approval” success messaging is absent and the fail-closed message remains.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| scripts/ci/test_strix_quick_gate.sh | Updates regression assertions to ensure approval publication cannot be treated as success and that fail-closed messaging remains. |
| .github/workflows/opencode-review.yml | Removes rate-limit soft-pass logic for APPROVE review publication and fails the job when the pull review cannot be published. |
Comments suppressed due to low confidence (1)
.github/workflows/opencode-review.yml:2903
- On pull-review publication failure, the script emits
::endgroup::unconditionally, butemit_review_body_to_action_logonly opens a::group::forREQUEST_CHANGESandINLINE_COMMENT_PUBLISH_FAILED. ForAPPROVEfailures this can produce an unmatchedendgroupin Actions logs. Gate theendgroupemission on the same event types (or move group closing intoemit_review_body_to_action_log).
printf '::error::OpenCode could not publish the pull review for head %s, so the review state was not changed.\n' "$HEAD_SHA"
echo "::endgroup::"
exit 1
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode reviewed the current-head mergeability evidence and changed-file flow before approval, then found merge conflicts on the affected path.
Findings
1. HIGH Merge Conflict Guidance - Resolve the PR branch against the latest base branch
- Problem: GitHub reports mergeStateStatus
DIRTYfor this pull request. - Root cause: Branch
codex/fail-approve-publish-without-reviewcannot be merged cleanly intomain; the changed-file flow below shows which review/runtime path is blocked by the conflict. - Fix: Merge or rebase the latest
mainintocodex/fail-approve-publish-without-review, resolve conflict markers in the PR branch, rerun the focused checks, and push the same branch. - Repair commands:
gh pr checkout 272 --repo ContextualWisdomLab/.github
git fetch origin main
git merge --no-ff origin/main # or: git rebase origin/main
git status --short
# resolve files, then git add <resolved-files>
# merge path: git commit
# rebase path: git rebase --continue
git push origin HEAD:codex/fail-approve-publish-without-review
# rebase path only: git push --force-with-lease origin HEAD:codex/fail-approve-publish-without-review- Regression test: Keep OpenCode approval gated on mergeability so model-output failures cannot approve a conflicted PR.
Merge Conflict Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> Conflict["Merge conflict blocks this path"]
Conflict --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> Conflict["Merge conflict blocks this path"]
Conflict --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> Conflict["Merge conflict blocks this path"]
Conflict --> V3["targeted test run"]
- Result: REQUEST_CHANGES
- Reason: mergeStateStatus is
DIRTY; mergeable isCONFLICTING. - Head SHA:
a392b9f769f8f77b9ba5eb75d591fea6e0ba9e02 - Workflow run: 28503462405
- Workflow attempt: 1
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> Conflict["Merge conflict blocks this path"]
Conflict --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> Conflict["Merge conflict blocks this path"]
Conflict --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> Conflict["Merge conflict blocks this path"]
Conflict --> V3["targeted test run"]
Contributor
OpenCode Review Overview
Pull request overviewOpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes. Findings1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
Summary
No PR approval was posted because model-output failure is not evidence that the PR has no blockers. Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line. Changed-File Evidence Mapflowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
|
Contributor
Author
|
@copilot resolve the merge conflicts in this pull request |
Contributor
Resolved the merge conflicts and merged |
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
063685c7c0be54ebb55ec946c34a0739be552c6f - Workflow run: 28512066276
- Workflow attempt: 2
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
Author
@copilot 고칩시다. re-kick을 하든, exponential retry를 하든.. 이렇게 하면 뭐 나더러 어쩌라고.. |
Contributor
반영했습니다. 모델 풀 결과가 |
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
1224db9dd75437f42e2b98f38107622a23d7cd31 - Workflow run: 28513538624
- Workflow attempt: 2
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
Author
@copilot 모델 부족이면 계속 exponential sleep 해서라도 반드시 성공시키자 |
Contributor
반영했습니다. 모델 풀 결과가 |
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28528202916
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28541870020
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28552741347
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28555964097
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28558954038
- Workflow attempt: 1
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
Contributor
There was a problem hiding this comment.
Pull request overview
OpenCode exhausted the configured model pool without a usable current-head review conclusion. This is not approval evidence, so the PR is blocked until a source-backed review can establish approval sufficiency or identify concrete fixes.
Findings
1. HIGH review evidence:1 - OpenCode could not establish approval sufficiency
- Problem: every configured model path failed to produce a usable current-head control block.
- Root cause: model execution, timeout, export, normalization, or approval-gate validation did not complete after exponential retry across the configured model pool.
- Impact: approving from deterministic check state alone would miss PR-intent mismatches, missing files, edge-case bugs, robustness gaps, UX/DX regressions, security issues, and CodeGraph-backed base/head flow changes.
- Fix: rerun OpenCode after model availability recovers, or update the PR with the missing files, tests, docs, generated artifacts, and verification evidence needed for a source-backed review conclusion.
- Regression test: keep the approval gate posting REQUEST_CHANGES, not APPROVE or check-only failure, when no model produces a valid current-head review.
Summary
- Result: REQUEST_CHANGES
- Reason: coverage-evidence passed and peer GitHub Checks completed without failures, but no model produced a valid review control block.
- Deterministic evidence checked but not used for approval: current-head changed-file evidence (.github/workflows/opencode-review.yml, scripts/ci/test_strix_quick_gate.sh, tests/test_opencode_agent_contract.py); coverage-evidence result success; peer checks from statusCheckRollup excluding this OpenCode check.
- Model outcome: model_pool=exhausted; selected_model=none.
- Head SHA:
3c3bf6dc619682f82b284ca760009ac154d55d13 - Workflow run: 28515588277
- Workflow attempt: 2
No PR approval was posted because model-output failure is not evidence that the PR has no blockers.
Inline comment note: OpenCode could not find an added RIGHT-side diff line for this PR, so the model-exhaustion blocker is attached to the PR review body instead of a file line.
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Workflow: opencode-review.yml"]
S1 --> I1["GitHub Actions review job"]
I1 --> R1["Review risk: Workflow: opencode-review.yml"]
R1 --> V1["actionlint plus required checks"]
Evidence --> S2["CI script: test_strix_quick_gate.sh"]
S2 --> I2["review and security gate shell path"]
I2 --> R2["Review risk: CI script: test_strix_quick_gate.sh"]
R2 --> V2["bash -n plus Strix self-test"]
Evidence --> S3["Test: test_opencode_agent_contract.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_opencode_agent_contract.py"]
R3 --> V3["targeted test run"]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Verification
Context
pg-erd-cloud #406 has an OpenCode APPROVE overview but no approving pull review, so branch protection still blocks merge. The required workflow must not hide that state.